Downloads: 2 | Views: 155 | Weekly Hits: ⮙1 | Monthly Hits: ⮙1
Research Paper | Mathematics and Statistics | Saudi Arabia | Volume 13 Issue 5, May 2024 | Popularity: 5 / 10
The Effect of Data Grouping on the Significance of the Coefficients of the Multiple Linear Regression Model
Adil Mousa Younis Waniss, Abdulmajied Ali Balkash
Abstract: This study is devoted for investigating the effect of grouping on the multiple linear regression coefficient's particularly on their significance, estimated confidence intervals and their standard error of the multiple linear regression coefficients, we generate random numbers from Excel and built multiple linear regression model with two independent variables, we compared regression coefficient's for an ungrouped multiple linear regression model with different five aggregated regression coefficient's, we find that, multiple linear regression coefficient's and their confidence intervals as well as the standard error of the multiple linear regression coefficients are unbiased for the different levels of grouping and except in case of grouping by less than five grouped a Sharpe decreases happened to their values. Grouping gives the same results for the regression coefficient for different groups, and for the different estimated confidence intervals as well as for standard error of regression coefficients. We find that grouping should not goes above twenty groups nor below five groups. The most important flinging is that, all regression coefficients for different groups are unbiased estimate and gives same p-values for different groups and different groups gives all most the same estimated confidence intervals and standard errors for the deferent multiple regression coefficients.
Keywords: data aggregation; regression coefficient's; confidence intervals; standard error of regression coefficients
Edition: Volume 13 Issue 5, May 2024
Pages: 1519 - 1524
DOI: https://www.doi.org/10.21275/ES24525085258
Please Disable the Pop-Up Blocker of Web Browser
Verification Code will appear in 2 Seconds ... Wait